Lead Python AI Solution Engineer

EPAM Systems Inc; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

EPAM Systems Inc is seeking a Lead Python AI Solution Engineer to design and deliver production AI and LLM applications in Python, shaping architecture and ensuring scalable, secure deployments. You will own RAG pipelines and AI agent frameworks while collaborating with client technology leadership to steer decisions.

The role emphasizes API integration, cloud deployment, and hands-on delivery with modern frameworks and container orchestration to support scalable AI products.

Qualifications

• 5+ years of professional software engineering experience with production AI/LLM apps.
• Strong Python 3.11/3.12+ proficiency.
• Experience with LangChain, LlamaIndex, and PydanticAI.
• Familiarity with Hugging Face models/datasets and tokenizers.
• Hands-on with uv/venv/Poetry, Ruff, Pytest, and Jupyter.
• ML libraries: NumPy, pandas/Polars, scikit-learn; DL: PyTorch, TensorFlow/Keras.
• Vector search and RAG infra: FAISS, Qdrant, Chroma, Weaviate, Milvus, pgvector.
• APIs and deployment: FastAPI, Uvicorn; Docker and Kubernetes; PostgreSQL/Redis/Kafka.
• English at least B2; TRL and DSPy familiarity are a plus.
• Portfolio: AI UI apps with Streamlit/Gradio/React/Next.js/Angular.

Responsibilities

• Design and deliver production-ready AI and LLM apps in Python.
• Develop RAG pipelines and AI agent architectures.
• Connect APIs for AI-driven capabilities and deploy across clouds.
• Collaborate with client tech leadership on direction and architecture.
• Prototype and prove AI concepts with modern frameworks and tools.
• Support experimentation and model tracking throughout the lifecycle.
• Translate business requirements into dependable technical implementations.

Skills

Python programming

AI/ML development

API design

Cloud deployment

English proficiency

RAG pipelines

LLM concepts

Architectural thinking

Analytical judgment

Prototyping

Tools

LangChain

LlamaIndex

PydanticAI

Hugging Face

tokenizers

uv

venv

Poetry

Ruff

Pytest

Jupyter

NumPy

pandas/Polars

scikit-learn

PyTorch

TensorFlow/Keras

FAISS

Qdrant

Chroma

Weaviate

Milvus

pgvector

FastAPI

Uvicorn

Docker

Kubernetes

PostgreSQL

Redis

Apache Kafka

Streamlit

Gradio

React

Next.js

Angular

Job description

We are looking for a Lead Python AI Solution Engineer to build production AI and LLM solutions, shape architecture and deliver reliable, scalable systems. You will lead Python-based RAG and agent work, integrate APIs, and partner with client technical leadership to steer decisions and delivery.

Responsibilities

• Design and deliver production-ready AI and LLM applications in Python
• Develop and sustain RAG pipelines along with AI agent architectures
• Implement and connect APIs that enable AI-driven capabilities
• Deploy and operate AI systems across cloud environments
• Ensure secure, scalable integration across platforms and services
• Collaborate with client Technical Leadership to set project direction and architecture
• Evaluate technical trade-offs with strong analytical judgment and recommend solutions
• Prototype and prove AI concepts using the right frameworks and tools
• Support experimentation and model tracking throughout the development lifecycle
• Translate business requirements into dependable technical implementations

Requirements

• 5+ years of professional software engineering experience, including substantial hands-on delivery of production AI and LLM applications
• High proficiency with Python 3.11/3.12+ as your primary programming language
• Deep experience with LLM application and agent frameworks such as LangChain, LlamaIndex, and PydanticAI
• Working knowledge of Hugging Face Models/Datasets, sentence-transformers, and tokenizers
• Hands-on familiarity with Python project and dependency tooling such as uv, venv, and Poetry
• Solid command of code quality and development tools including Ruff, Pytest, and Jupyter
• Strong background with machine learning libraries such as NumPy, pandas/Polars, and scikit-learn
• Practical understanding of deep learning frameworks such as PyTorch and TensorFlow/Keras
• Proven track record implementing vector search and RAG infrastructure such as FAISS, Qdrant, Chroma, Weaviate, Milvus, or pgvector with PostgreSQL
• Hands-on experience building AI APIs and deployment components with FastAPI, Pydantic, and Uvicorn
• Demonstrated skills in containerization and orchestration using Docker and Kubernetes
• Experience working with data infrastructure technologies such as PostgreSQL, Redis, and Apache Kafka
• English proficiency at B2 level (Upper-Intermediate) or higher
• Nice to have Experience applying TRL for LLM post-training
• Knowledge of DSPy for building programmatic LLM pipelines
• Familiarity with LiteLLM to unify access to multiple LLM APIs
• Experience with experiment tracking tools such as MLflow and Weights & Biases
• Portfolio of AI application UI work using Streamlit, Gradio, or FastAPI with React/Next.js/Angular 19+